---
title: CenterNet-Pose
canonical_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-Pose"
md_url: "https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-Pose.md"
repository: Qualcomm-AI-Hub/CenterNet-Pose
last_updated: 2026-10-16
license: mit
downloads: 0
stars: 0
tags:
  - android
---

# CenterNet-Pose

> CenterNet-Pose - Qualcomm-AI-Hub 在 ModelScope 开源的模型。CenterNet-Pose: Optimized for Qualcomm Devices

Qualcomm-AI-Hub/CenterNet-Pose 是 ModelScope 魔搭社区上的机器学习模型，采用 mit 许可。

- **Repository**: Qualcomm-AI-Hub/CenterNet-Pose
- **License**: mit
- **Tags**: android
- **Downloads**: 0
- **Stars**: 0
- **Last updated**: 2026-10-16

Source: https://www.modelscope.cn/models/Qualcomm-AI-Hub/CenterNet-Pose

---

![](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/web-assets/model_demo.png)

# CenterNet-Pose: Optimized for Qualcomm Devices

CenterNet-Pose is a machine learning model that detects human pose and returns a location and confidence for each of 17 joints.

This is based on the implementation of CenterNet-Pose found [here](https://github.com/xingyizhou/CenterNet).
This repository contains pre-exported model files optimized for Qualcomm® devices. You can use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/centernet_pose) library to export with custom configurations. More details on model performance across various devices, can be found [here](#performance-summary).

Qualcomm AI Hub Models uses [Qualcomm AI Hub Workbench](https://workbench.aihub.qualcomm.cn) to compile, profile, and evaluate this model. [Sign up](https://myaccount.qualcomm.com/signup) to run these models on a hosted Qualcomm® device.

## Getting Started
There are two ways to deploy this model on your device:

### Option 1: Download Pre-Exported Models

Below are pre-exported model assets ready for deployment.

| Runtime | Precision | Chipset | SDK Versions | Download |
|---|---|---|---|---|
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_snapdragon_x2_elite.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_snapdragon_x_elite.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen3.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_snapdragon_8gen1.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_qcs8275.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_qcs8550_proxy.zip)
| PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_qcs9075.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45, ONNX Runtime 1.27.1 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-precompiled_qnn_onnx-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_snapdragon_x2_elite.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_snapdragon_x_elite.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_snapdragon_8gen3.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_snapdragon_8gen1.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_qcs8275.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_qcs8550_proxy.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_sa8775p.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_qcs9075.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_sa7255p.zip)
| QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_sa8295p.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_snapdragon_8_elite_for_galaxy.zip)
| QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | QAIRT 2.45 | [Download](https://china-qaihub-public-assets.s3.cn-northwest-1.amazonaws.com.cn/qai-hub-models/models/centernet_pose/releases/v0.62.1/centernet_pose-qnn_context_binary-float-qualcomm_snapdragon_8_elite_gen5_for_galaxy.zip)

For more device-specific assets and performance metrics, visit **[CenterNet-Pose on Qualcomm® AI Hub](https://aihub.qualcomm.cn/models/centernet_pose)**.


### Option 2: Export with Custom Configurations

Use the [Qualcomm® AI Hub Models](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/centernet_pose) Python library to compile and export the model with your own:
- Custom weights (e.g., fine-tuned checkpoints)
- Custom input shapes
- Target device and runtime configurations

This option is ideal if you need to customize the model beyond the default configuration provided here.

See our repository for [CenterNet-Pose on GitHub](https://github.com/qualcomm/ai-hub-models-cn/blob/main/src/qai_hub_models/models/centernet_pose) for usage instructions.

## Model Details

**Model Type:** Model_use_case.pose_estimation

**Model Stats:**
- Input resolution: 1 x 3 x 512 x 512
- Model checkpoint: multi_pose_dla_3x.pth
- Model size: 57.8 MB
- Number of parameters: 20.6M

## Performance Summary
| Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
|---|---|---|---|---|---|---
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® X2 Elite | 22.451 ms | 4 - 4 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® X Elite | 51.291 ms | 44 - 44 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 3 Mobile | 34.129 ms | 4 - 11 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Gen 1 Mobile | 97.333 ms | 4 - 18 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-8275 | 46.565 ms | 3 - 7 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 50.56 ms | 4 - 5 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® QCS8450 | 97.333 ms | 4 - 18 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-9075 | 51.516 ms | 3 - 6 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ IQ-X7181 | 51.291 ms | 44 - 44 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Qualcomm® Dragonwing™ Q-8750 | 26.734 ms | 4 - 14 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Mobile | 26.734 ms | 4 - 14 MB | NPU
| CenterNet-Pose | PRECOMPILED_QNN_ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 22.415 ms | 3 - 12 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® X2 Elite | 22.618 ms | 1 - 1 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® X Elite | 51.423 ms | 1 - 1 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 3 Mobile | 34.237 ms | 1 - 8 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Gen 1 Mobile | 97.231 ms | 1 - 11 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-8275 | 46.469 ms | 1 - 5 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ QCS8550 (Proxy) | 49.872 ms | 1 - 4 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA8775P | 51.671 ms | 1 - 10 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA8650P | 51.671 ms | 1 - 10 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA8255P | 51.671 ms | 1 - 10 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® QCS8450 | 97.231 ms | 1 - 11 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-9075 | 52.064 ms | 1 - 4 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ IQ-X7181 | 51.423 ms | 1 - 1 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® Dragonwing™ Q-8750 | 26.661 ms | 1 - 14 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA7255P | 91.437 ms | 1 - 9 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Qualcomm® SA8295P | 60.814 ms | 0 - 5 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Mobile | 26.661 ms | 1 - 14 MB | NPU
| CenterNet-Pose | QNN_CONTEXT_BINARY | float | Snapdragon® 8 Elite Gen 5 Mobile | 22.405 ms | 1 - 9 MB | NPU

## License
* The license for the original implementation of CenterNet-Pose can be found
  [here](https://github.com/xingyizhou/CenterNet/blob/master/LICENSE).

## References
* [Objects as Points](https://arxiv.org/abs/1904.07850)
* [Source Model Implementation](https://github.com/xingyizhou/CenterNet)

## Community
* For questions or feedback, chat with our engineers in [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.cn).